Tag
This paper proposes Cognitive Field Networks (CFNs), a recurrent Transformer architecture for continuous cognitive dynamics that enables persistent, history-dependent cognition without explicit memory systems, inspired by biologically inspired theories.
This paper introduces The Unwritten Benchmark, a new challenge to evaluate abstract perceptual reasoning in multimodal AI models, revealing a significant performance gap between humans and current models like GPT-4o and Gemini 2.5-Pro.